Abstract
With the overwhelming volume of online multimedia content and increasing ubiquity of Internet-enabled mobile devices, pervasive use of the Web for content sharing and consumption has become our everyday routines. Consequently, people seeking online access to content of interest are becoming more and more frustrated. Thus, deciding which content to consume among the deluge of available alternatives becomes increasingly difficult. Context-aware personalization, having the capability to predict user's contextual preferences, has been proposed as an effective solution. However, some existing personalized systems, especially those based on collaborative filtering, rely on rating information explicitly obtained from users in consumption contexts. Therefore, these systems suffer from the so-called cold-start problem that occurs as a result of personalization systems' lack of adequate knowledge of either a new user's preferences or of a new item rating information. This happens because these new items and users have not received or provided adequate rating information respectively. In this paper, we present an analysis and design of a context-aware personalized system capable of minimizing new user cold-start problem in a mobile multimedia consumption scenario. The article emphasizes the importance of similarity between contexts of consumption based on the traditional k-nearest neighbor algorithm using Pearson Correlation model. Experimental validation, with respect to quality of personalized recommendations and user satisfaction in both contextual and non-contextual scenarios, shows that the proposed system can mitigate the effect of user-based cold-start problem.

Abstract
Multimedia adaptation depends on several factors, such as the content itself, the consumption device and its characteristics, the transport and access networks and the user. An adaptation decision engine, in order to provide the best possible Quality of Experience to a user, needs to have information about all variables that may influence its decision. For the aforementioned factors, we implement content classification, define device classes, consider limited bandwidth scenarios and categorize user preferences based on a subjective quality evaluation test. The results of these actions generate vital information to pass to the adaptation decision engine so that its operation may provide the indication of the most suitable adaptation to perform that delivers the best possible outcome for the user under the existing constraints.

Abstract
Many embedded applications process large amounts of data using regular computational kernels, amenable to acceleration by specialized hardware coprocessors. To reduce the significant design effort, the dedicated hardware may be automatically generated, usually starting from the application's source or binary code. This paper presents a moduloscheduled loop accelerator capable of executing multiple loops and a supporting toolchain. A generation/scheduling procedure, which fully relies on MicroBlaze instruction traces, produces accelerator instances, customized in terms of functional units and interconnections. The accelerators support integer and single-precision floating-point arithmetic, and exploit instruction-level parallelism, loop pipelining, and memory access parallelism via two read/write ports. A complete implementation of the proposed architecture is evaluated in a Virtex-7 device. Augmenting a MicroBlaze processor with a tailored accelerator achieves a geometric mean speedup, over software-only execution, of 6.61x for 13 floating-point kernels from the Livermore Loops set, and of 4.08x for 11 integer kernels from Texas Instruments' IMGLIB. The proposed customized accelerators are compared with ALU-based ones. The average specialized accelerator requires only 0.47x the number of field-programmable gate array slices of an accelerator with four ALUs. A geometric mean speedup of 1.78x over a four-issue very long instruction word (without floating-point support) was obtained for the integer kernels.

Abstract
This paper describes the design and implementation of a coarse-grained reconfigurable array (CGRA) for low-power biological signal processing. It uses an use-case-driven approach which explores the application domain and gathers common requirements. The selected CGRA core architecture is implemented using a standard-cell flow (in a generic 90nm CMOS process), so that the CGRA can be totally or partially turned off by power gating. The selected CGRA design is evaluated for two use-cases using layout information and accurate node activity information. The resulting accelerator is capable of performing various signal processing tasks very efficiently, achieving an average power consumption of 19.9 pJ/cycle (or 1.99mW at 100 MHz). Static power consumption for less intensive tasks can be reduced by using only some sections of the CGRA while powering-off others.

Abstract

Abstract
Filter-bank Multicarrier (FBMC) modulation has been proposed as a 5G waveform candidate due to its better spectral efficiency and lower out-of-band emissions compared to OFDM. This paper presents an FPGA-based implementation of a Frequency Spreading FBMC-OQAM baseband modulator and evaluates it in terms of performance, resource utilization and power consumption. The proposed system is then compared with published Polyphase Network (PPN) FBMC-OQAM designs, focusing on resource utilization. The results suggest that the higher computational complexity of FS-FBMC systems does not directly result in higher resource utilization, which makes FS-FBMC a convenient scheme for implementing FBMC designs on FPGA.